Iskra Dukovska-Popovska
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Iskra Dukovska-Popovska has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Claudio Sassanelli
Politecnico di Bari
5 shared publications - Adriana Hofmann Trevisan
Politecnico di Milano
4 shared publications - Federica Acerbi
Politecnico di Milano
4 shared publications - Riikka Kaipia
VTT Technical Research Centre of Finland Ltd
3 shared publications - Sergio Terzi
Politecnico di Milano
3 shared publications - Heidi Carin Dreyer
NTNU
2 shared publications
Latest Publications
- Open Access
- 2 July 2026
- Published by Elsevier in SSRN Electronic Journal
From Data to Decisions in Surgery Scheduling: Machine Learning and Simulation for Sequencing Arthroplasty Patients
Purpose Efficient operating room (OR) scheduling depends on accurate prediction of duration of surgery (DOS) and effective sequencing strategies. In high-volume arthroplasty procedures, reliance on averages or surgeons’ DOS estimates can cause inefficiencies in resource allocation. This study develops an integrated framework combining machine learning (ML) DOS prediction with discrete-event simulation (DES) to support evidence-based sequencing and scheduling decisions. Design/methodology/approach A dataset of 3,233 hip and knee arthroplasty cases was analyzed using preoperative clinical, operational, and temporal features. Multiple ML models were tested for DOS prediction; performance and feature importance were evaluated using accuracy metrics, SHAP values, and partial dependence. Predicted DOS values were then applied within DES to compare sequencing strategies and assess impacts on completion times, and overtime in marginal conditions. Findings Extreme Gradient Boosting achieved the best predictive accuracy (Mean Absolute Error = 12.86, Root Mean Squared Error = 16.67, Buffer Accuracy = 68.73). Surgeon, procedure type, and temporal variables were key predictors. Simulation experiments revealed that no single sequencing strategy consistently minimized finish times; effectiveness depended on patient-specific and contextual factors. Marginal condition analysis identified opportunities for improved OR utilization and reduced overtime through tailored sequencing policies. Originality/value This study uniquely integrates ML-based DOS prediction with simulation-driven sequencing evaluation in arthroplasty surgery. The framework advances beyond subjective or average-based planning by enabling data-driven, case-specific scheduling. The approach is adaptable to other surgical specialties and can incorporate additional predictors or real-time data, offering a novel pathway toward intelligent scheduling systems that balance clinical priorities with operational efficiency.
- 2 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessFrom Data to Decisions in Surgery Scheduling: Machine Learning and Simulation for Sequencing Arthroplasty Patients
Purpose Efficient operating room (OR) scheduling depends on accurate prediction of duration of surgery (DOS) and effective sequencing strategies. In high-volume arthroplasty procedures, reliance on averages or surgeons’ DOS estimates can cause inefficiencies in resource allocation. This study develops an integrated framework combining machine learning (ML) DOS prediction with discrete-event simulation (DES) to support evidence-based sequencing and scheduling decisions. Design/methodology/approach A dataset of 3,233 hip and knee arthroplasty cases was analyzed using preoperative clinical, operational, and temporal features. Multiple ML models were tested for DOS prediction; performance and feature importance were evaluated using accuracy metrics, SHAP values, and partial dependence. Predicted DOS values were then applied within DES to compare sequencing strategies and assess impacts on completion times, and overtime in marginal conditions. Findings Extreme Gradient Boosting achieved the best predictive accuracy (Mean Absolute Error = 12.86, Root Mean Squared Error = 16.67, Buffer Accuracy = 68.73). Surgeon, procedure type, and temporal variables were key predictors. Simulation experiments revealed that no single sequencing strategy consistently minimized finish times; effectiveness depended on patient-specific and contextual factors. Marginal condition analysis identified opportunities for improved OR utilization and reduced overtime through tailored sequencing policies. Originality/value This study uniquely integrates ML-based DOS prediction with simulation-driven sequencing evaluation in arthroplasty surgery. The framework advances beyond subjective or average-based planning by enabling data-driven, case-specific scheduling. The approach is adaptable to other surgical specialties and can incorporate additional predictors or real-time data, offering a novel pathway toward intelligent scheduling systems that balance clinical priorities with operational efficiency.
- 1 May 2026
- Published by Springer Nature
- p. 489-501
Educating for the Circular Economy Era: A Course on End-of-Life Product Management
- 1 May 2026
- Published by Springer Nature
- p. 489-501
Educating for the Circular Economy Era: A Course on End-of-Life Product Management
- Open Access
- 21 November 2025
- Published by Elsevier in Technology in Society
- Vol. 85
Teaching methods for building human capital for the twin transition: a skill-based approach
- 21 November 2025
- Published by Elsevier in Technology in Society
- Vol. 85
Open AccessTeaching methods for building human capital for the twin transition: a skill-based approach
- 25 July 2025
- Published by Springer Nature
- p. 207-220
A Research Agenda Advancing Circular Economy Skills
- 25 July 2025
- Published by Springer Nature
- p. 207-220
A Research Agenda Advancing Circular Economy Skills
- 27 March 2025
- Published by Emerald Publishing in International Journal of Physical Distribution & Logistics Management
- Vol. 55 (5) , 482-504
End-of-life textile collection from consumers: a design science approach
Purpose: Separate collection of end-of-life (EoL) textiles is considered a prerequisite for an effective circular textile system. This study aims to examine how the design of a collection system for EoL textiles facilitates high collection quantities and sorting qualities.Design/methodology/approach: A design science approach using context–intervention–mechanisms–outcome logic was applied, as the study addresses a practical problem and provides suggestions for designing a collection system for EoL textiles. Nine collection pilots in the Nordic countries were designed, empirically tested and analyzed.Findings: When designing a collection system for EoL textiles, it is important to consider consumers’ convenience and awareness as well as collectors’ efficiency. Proximity of collection to households results in high collection quantity per household, triggering the mechanisms of consumer convenience and awareness. Indoor collection improves the sorting quality and quantity of the reusable textile fraction due to the trust of keeping the material value. Collection close to the consumer supported with clear and continuous communication can result in high sorting quality of the recyclable textile fraction. Consumers’ sorting quality can improve with time, thereby increasing the overall efficiency of the reverse EoL textile value chain. Semi-centralized collection best meets the requirements of both consumers and collectors.Originality/value: This study contributes to the knowledge of circular supply chain management by providing empirical results and evaluating real-life solutions to the first-mile problem of reverse flows of EoL textiles. The results offer insights into the design elements of EoL textile collection systems and identify what facilitates high collection quantity and quality of sorting.
- 27 March 2025
- Published by Emerald Publishing in International Journal of Physical Distribution & Logistics Management
- Vol. 55 (5) , 482-504
End-of-life textile collection from consumers: a design science approach
Purpose: Separate collection of end-of-life (EoL) textiles is considered a prerequisite for an effective circular textile system. This study aims to examine how the design of a collection system for EoL textiles facilitates high collection quantities and sorting qualities.Design/methodology/approach: A design science approach using context–intervention–mechanisms–outcome logic was applied, as the study addresses a practical problem and provides suggestions for designing a collection system for EoL textiles. Nine collection pilots in the Nordic countries were designed, empirically tested and analyzed.Findings: When designing a collection system for EoL textiles, it is important to consider consumers’ convenience and awareness as well as collectors’ efficiency. Proximity of collection to households results in high collection quantity per household, triggering the mechanisms of consumer convenience and awareness. Indoor collection improves the sorting quality and quantity of the reusable textile fraction due to the trust of keeping the material value. Collection close to the consumer supported with clear and continuous communication can result in high sorting quality of the recyclable textile fraction. Consumers’ sorting quality can improve with time, thereby increasing the overall efficiency of the reverse EoL textile value chain. Semi-centralized collection best meets the requirements of both consumers and collectors.Originality/value: This study contributes to the knowledge of circular supply chain management by providing empirical results and evaluating real-life solutions to the first-mile problem of reverse flows of EoL textiles. The results offer insights into the design elements of EoL textile collection systems and identify what facilitates high collection quantity and quality of sorting.
- Open Access
- 15 September 2024
- Published by Elsevier in International Journal of Medical Informatics
- Vol. 192, 105631
Machine learning for predicting duration of surgery and length of stay: A literature review on joint arthroplasty
- 15 September 2024
- Published by Elsevier in International Journal of Medical Informatics
- Vol. 192, 105631
Open AccessMachine learning for predicting duration of surgery and length of stay: A literature review on joint arthroplasty
- Top Cited PapersOpen Access
- 7 September 2024
- Published by Elsevier in Journal of Cleaner Production
- Vol. 474
Skills for the twin transition in manufacturing: A systematic literature review
- 7 September 2024
- Published by Elsevier in Journal of Cleaner Production
- Vol. 474
Top Cited PapersOpen AccessSkills for the twin transition in manufacturing: A systematic literature review
- 7 September 2024
- Published by Springer Nature
- p. 262-274
Market Needs for a Circular Transition: Implemented Practices and Required Skills
- 7 September 2024
- Published by Springer Nature
- p. 262-274
Market Needs for a Circular Transition: Implemented Practices and Required Skills
- Open Access
- 8 February 2023
- Published by Elsevier in Waste Management
- Vol. 159, 154-162
The supply and demand balance of recyclable textiles in the Nordic countries
- 8 February 2023
- Published by Elsevier in Waste Management
- Vol. 159, 154-162
Open AccessThe supply and demand balance of recyclable textiles in the Nordic countries
- Open Access
- 8 February 2018
- Published by Emerald Publishing in International Journal of Physical Distribution & Logistics Management
- Vol. 48 (2) , 114-138
Proposals for enhancing tactical planning in grocery retailing with S&OP
Purpose: The purpose of this paper is to explore tactical planning in grocery retailing and propose how process and integration mechanisms from sales and operations planning (S&OP) can enhance retail tactical planning. Design/methodology/approach: This work follows an explorative design with case studies from the grocery retailing industry in Finland, Norway, and the UK. Findings: The tactical planning process focuses on demand management and securing product availability from suppliers in order to reach sales targets. Less attention is directed toward balancing supply and demand or toward providing a single plan to guide company operations. Planning appeared to be functionally oriented with limited coordination between functional plans, but it did include external integration that improved forecast accuracy. Research limitations/implications: The study involves grocery retailer cases with variable levels of S&OP maturity. The propositions need to be investigated further through action research or additional case studies to confirm their validity. Practical implications: The study proposes a design of an S&OP process in retailing and propositions for improving tactical planning integration. Originality/value: The study complements research on retail tactical planning by taking planning process and integration viewpoints. The research suggests that retailers would benefit from a formal and company-wide S&OP process to unify different market-oriented plans to a single set of numbers, thus better balancing supply and demand without sacrificing the emphasis on demand planning.
- 8 February 2018
- Published by Emerald Publishing in International Journal of Physical Distribution & Logistics Management
- Vol. 48 (2) , 114-138
Open AccessProposals for enhancing tactical planning in grocery retailing with S&OP
Purpose: The purpose of this paper is to explore tactical planning in grocery retailing and propose how process and integration mechanisms from sales and operations planning (S&OP) can enhance retail tactical planning. Design/methodology/approach: This work follows an explorative design with case studies from the grocery retailing industry in Finland, Norway, and the UK. Findings: The tactical planning process focuses on demand management and securing product availability from suppliers in order to reach sales targets. Less attention is directed toward balancing supply and demand or toward providing a single plan to guide company operations. Planning appeared to be functionally oriented with limited coordination between functional plans, but it did include external integration that improved forecast accuracy. Research limitations/implications: The study involves grocery retailer cases with variable levels of S&OP maturity. The propositions need to be investigated further through action research or additional case studies to confirm their validity. Practical implications: The study proposes a design of an S&OP process in retailing and propositions for improving tactical planning integration. Originality/value: The study complements research on retail tactical planning by taking planning process and integration viewpoints. The research suggests that retailers would benefit from a formal and company-wide S&OP process to unify different market-oriented plans to a single set of numbers, thus better balancing supply and demand without sacrificing the emphasis on demand planning.